{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/producing-augmentation-invariant-embeddings","title":"Producing augmentation-invariant embeddings from real-life imagery","arxiv_id":"2112.03415","date":"2021-12-06","proceeding":null,"authors":["Sergio Manuel Papadakis","Sanjay Addicam"],"abstract":"This article presents an efficient way to produce feature-rich, high-dimensionality embedding spaces from real-life images. The features produced are designed to be independent from augmentations used in real-life cases which appear on social media. Our approach uses convolutional neural networks (CNN) to produce an embedding space. An ArcFace head was used to train the model by employing automatically produced augmentations. Additionally, we present a way to make an ensemble out of different embeddings containing the same semantic information, a way to normalize the resulting embedding using an external dataset, and a novel way to perform quick training of these models with a high number of classes in the ArcFace head. Using this approach we achieved the 2nd place in the 2021 Facebook AI Image Similarity Challenge: Descriptor Track.","url_abs":"https://arxiv.org/abs/2112.03415v2","url_pdf":"https://arxiv.org/pdf/2112.03415v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"producing-augmentation-invariant-embeddings","repo_url":"https://github.com/socom20/facebook-image-similarity-challenge-2021","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"arcface","method_name":"ArcFace"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.03415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03415"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/socom20/facebook-image-similarity-challenge-2021","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7b73002230abc9ea","entry":"cos_decay","repo":"socom20/facebook-image-similarity-challenge-2021","repo_kind":"official","path":"modules/Facebook_model_AFMultiGPU_v22.py","file_url":"https://github.com/socom20/facebook-image-similarity-challenge-2021/blob/HEAD/modules/Facebook_model_AFMultiGPU_v22.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b73002230abc9ea"}},{"code_sha256_prefix":"97d3926abdb281c0","entry":"flip","repo":"socom20/facebook-image-similarity-challenge-2021","repo_kind":"official","path":"modules/Facebook_AFMultiGPU_model_v23_sy_v6.py","file_url":"https://github.com/socom20/facebook-image-similarity-challenge-2021/blob/HEAD/modules/Facebook_AFMultiGPU_model_v23_sy_v6.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"97d3926abdb281c0"}},{"code_sha256_prefix":"6eb906f418ecceca","entry":"l2_norm","repo":"socom20/facebook-image-similarity-challenge-2021","repo_kind":"official","path":"modules/Facebook_AFMultiGPU_model_v23_sy_v6.py","file_url":"https://github.com/socom20/facebook-image-similarity-challenge-2021/blob/HEAD/modules/Facebook_AFMultiGPU_model_v23_sy_v6.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6eb906f418ecceca"}},{"code_sha256_prefix":"3c996e923769005a","entry":"seed_everything","repo":"socom20/facebook-image-similarity-challenge-2021","repo_kind":"official","path":"modules/Facebook_AFMultiGPU_model_v23_sy_v6.py","file_url":"https://github.com/socom20/facebook-image-similarity-challenge-2021/blob/HEAD/modules/Facebook_AFMultiGPU_model_v23_sy_v6.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c996e923769005a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}